Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/isaacriehm/cairnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/isaacriehm/cairn/cairn-direction)<a href="https://agentmods.dev/commands/isaacriehm/cairn/cairn-direction"><img src="https://agentmods.dev/badge/commands/isaacriehm/cairn/cairn-direction/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/isaacriehm/cairn/cairn-direction"><img src="https://agentmods.dev/badge/commands/isaacriehm/cairn/cairn-direction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.00245 |
| Opus 5.5 | $0.00008 | $0.00098 |
| Sonnet 5.5 | $0.00004 | $0.00049 |
| Haiku 4.5 | $0.00002 | $0.00024 |
Grade A, and why
cairn-direction scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/cairn:cairn-direction
Manually trigger the cairn-direction skill on the argument prompt.
Equivalent to the auto-invoked path but bypasses the trigger gate.
Behavior
Treat the slash-command argument as the operator's task prompt. Invoke
the cairn-direction skill with that prompt. The skill runs its
normal pipeline — gather in-scope context, ask load-bearing questions,
write tightened spec, dispatch chunks.
If the argument is empty:
/cairn:cairn-direction needs a task description. Example:
/cairn:cairn-direction add a webhook for stripe disputes
When to use
- The operator's prior message was conversational ("can we talk about X") but the operator now wants Cairn to take it as a task.
- Auto-invoke skipped a borderline message (read-only at a glance, but actually a refactor request).
- Forcing tightening on a partially-specified prompt to surface its ambiguities before writing code.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 30 lines · 19 tokens per session scan A 0e4fe5f5207f
cairn-direction is a command published in the GitHub repository isaacriehm/cairn (6 stars, last pushed 14d ago), licensed MIT. It adds 19 tokens to every session and 245 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
tour
Tour this project's memory — what's captured, where it lives, how to recall it (core-memory-kit).
rosetta-grill
Grill the user about a plan or design — but grounded in Rosetta's resolved decision state — then RECORD the outcome as an ADR/PDR. Use when the user wants to stress-test a decision, says "grill me on this", or wants a decision interrogated and captured. Integrates grill-me-style interrogation with Rosetta's…
rosetta-preflight
Produce Rosetta's deterministic preflight JSON for a scoped change: optional RA1 structural report, decision-state resolution, and local Rosetta gates. Use before handing execution to a loop runner.
seed
Inspect the codebase and propose starter areas + topics for the wherefore log.
reflect
Synthesize patterns and a progress summary from milepost entries.
remember
Store something in the appropriate memory file. This command is the smart router for the memory system.